CN116616771A - Multichannel simple mental state detection method, device and system - Google Patents
Multichannel simple mental state detection method, device and system Download PDFInfo
- Publication number
- CN116616771A CN116616771A CN202310587769.7A CN202310587769A CN116616771A CN 116616771 A CN116616771 A CN 116616771A CN 202310587769 A CN202310587769 A CN 202310587769A CN 116616771 A CN116616771 A CN 116616771A
- Authority
- CN
- China
- Prior art keywords
- bitmap data
- data
- time domain
- bitmap
- electroencephalogram
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 230000006996 mental state Effects 0.000 title claims abstract description 45
- 238000010276 construction Methods 0.000 claims description 26
- 238000006243 chemical reaction Methods 0.000 claims description 22
- 230000005284 excitation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 18
- 238000004364 calculation method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 abstract description 3
- 238000012549 training Methods 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 6
- 210000004556 brain Anatomy 0.000 description 5
- 201000000980 schizophrenia Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000763 evoking effect Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 230000003340 mental effect Effects 0.000 description 3
- 208000020016 psychiatric disease Diseases 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000001154 acute effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000001314 paroxysmal effect Effects 0.000 description 2
- 230000002085 persistent effect Effects 0.000 description 2
- 230000001766 physiological effect Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000010827 pathological analysis Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000021317 sensory perception Effects 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Psychology (AREA)
- Neurology (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Social Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Educational Technology (AREA)
- Neurosurgery (AREA)
- Physiology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a multichannel simple mental state detection method, device and system. Converting the electroencephalogram time domain data to be detected and each group of electroencephalogram time domain data into bitmap data with the same format by acquiring a multichannel electroencephalogram time domain data set, reserving bitmap data with higher similarity in each group of bitmap data, discarding bitmap data with lower similarity, constructing a feature library by the reserved bitmap data, performing exclusive-or operation on the bitmap data to be detected and the bitmap data in the feature library, and outputting the bitmap data with the operation result of 0 corresponding mental state. The invention simplifies the structure of the electroencephalogram features, reduces the requirement on the storage space of the system, does not need training and learning processes, has high arithmetic capability of the obtained features, can obtain an arithmetic result by directly carrying out logic operation on the features, has simple calculation model and high calculation efficiency, and improves the feasibility of the portable detection system.
Description
Technical Field
The invention relates to the field of auxiliary diagnosis and classification of psychiatric diseases, in particular to a multichannel simple mental state detection method, device and system.
Background
The abnormal condition of mental state is divided into acute transient abnormal condition, paroxysmal abnormal condition and persistent abnormal condition, in pathological analysis, the acute transient abnormal condition is sudden onset and short duration of mental abnormality, usually without diagnosis of mental disease, after rest and treatment, the two abnormal conditions of paroxysmal and persistent are mostly indicative of the individual suffering from mental related diseases, such as schizophrenia. Schizophrenia belongs to a syndrome with unknown etiology, and relates to multiple disorders such as sensory perception, personal consciousness, emotion, behavior and the like. The disease has no sign before onset, is related to a plurality of factors such as environment, psychology, individuals and the like, and has higher potential hidden trouble for patients and family members of the patients.
At present, the mental diseases such as schizophrenia and the like are difficult to directly diagnose by an instrument, the identification of the existing mental conditions of individuals depends on face-to-face inquiry of psychiatric doctors, comprehensive judgment is carried out by combining clinical experience, objective evaluation indexes are lacking as evidence, and if patients deliberately hide or lie and report own illness, the final diagnosis result of the doctors can be greatly influenced.
The currently widely accepted detection mode is that the test data obtained by an electroencephalogram (EEG) technology is most common, and can reflect the physiological change condition of the brain of a patient in the time dimension in a concentrated way, so that the degree of coincidence with the logical relationship of the physiological activity of the patient is high. The most widely used electroencephalogram technique is an evoked electroencephalogram technique, which obtains a change in the bioelectrical potential of the brain of a patient by stimulating the patient under external conditions such as vision and hearing, and there are frequently used Visual Evoked Potentials (VEP), auditory Evoked Potentials (AEP), P300, and the like.
At present, a more-used auxiliary diagnosis method is to train a classifier through characteristic data obtained from an electroencephalogram, and then learn and classify the electroencephalogram characteristics of a subject by utilizing the classifier so as to obtain a classification result. For example, a method for assisting diagnosis and classification of schizophrenia based on electroencephalogram time domain data is disclosed in the document CN109671500 a.
The diagnosis classification method using machine learning needs to extract complex features from the electroencephalogram of the volunteer patient and the electroencephalogram of the patient to be tested, and in the training and learning stage, the features need to be calculated more fussy, a detection system needs to be provided with a larger storage space and a processor with higher computation power, and when the classification is performed, the computation amount (computation load) of the system is also higher, so that the application scene with the requirements of portability and high efficiency obviously does not meet the requirements.
Disclosure of Invention
The invention aims at: in order to solve the above-mentioned problems, a multi-channel simple mental state detection method is provided to simplify the electroencephalogram feature, and a general detection result is rapidly calculated with less calculation effort and memory resource consumption.
The technical scheme adopted by the invention is as follows:
the invention provides a multichannel simple mental state detection method, which comprises the following steps:
acquiring a multi-channel electroencephalogram time domain data set, wherein the multi-channel electroencephalogram time domain data set comprises a plurality of groups of electroencephalogram time domain data, and each group of electroencephalogram time domain data comprises electroencephalogram time domain data respectively obtained for a plurality of individuals under the same group of excitation conditions;
converting each electroencephalogram time domain data in each group of electroencephalogram time domain data into bitmap data in the same format, and obtaining a group of bitmap data by one group of electroencephalogram time domain data;
for each set of bitmap data, calculating the similarity with the first bitmap data in sequence from the second bitmap data, if the similarity reaches a preset value and is not completely the same, reserving the bitmap data, otherwise discarding the bitmap data, and finally, constructing a feature library by each reserved set of bitmap data;
converting the electroencephalogram time domain data to be detected into bitmap data with the same format as bitmap data in a feature library to obtain bitmap data to be detected; and carrying out exclusive OR operation on the bitmap data to be detected and each piece of bitmap data in the feature library in sequence, and judging the state corresponding to the electroencephalogram time domain data if the operation result is 0.
Further, the converting each piece of electroencephalogram time domain data in each group of electroencephalogram time domain data into bitmap data in the same format includes:
the following processing is performed on each piece of electroencephalogram time domain data in each group of electroencephalogram time domain data:
performing time-frequency conversion on the electroencephalogram time domain data to obtain electroencephalogram frequency domain data;
and sequencing and segmenting the electroencephalogram frequency domain data from low frequency to high frequency, binarizing each segment of frequency domain data with a preset power threshold value, and sequencing each bit after binarization in sequence to obtain bitmap data.
Further, the step of sequentially calculating the similarity with the first piece of bitmap data from the second piece of bitmap data, and when the similarity reaches a predetermined value, reserving the piece of bitmap data, otherwise discarding the piece of bitmap data, includes:
and (3) starting from the second bitmap data, sequentially carrying out exclusive OR operation with the first bitmap data, and when the number of bits of 1 in the operation result does not exceed the preset number and the operation result is not 0, reserving the bitmap data, otherwise discarding the bitmap data.
Further, the number of bitmap data corresponding to each group of electroencephalogram time domain data is set to be the maximum value; when the number of bitmap data obtained reaches the maximum value, all bitmap data after the bitmap data is discarded.
The invention also provides a multichannel simple mental state detection device, which comprises a data acquisition module, a bitmap conversion module, a feature library construction module and a feature detection module, wherein:
the data acquisition module is configured to: acquiring a multi-channel electroencephalogram time domain data set, wherein the multi-channel electroencephalogram time domain data set comprises a plurality of groups of electroencephalogram time domain data, and each group of electroencephalogram time domain data comprises electroencephalogram time domain data respectively obtained for a plurality of individuals under the same group of excitation conditions;
the bitmap conversion module is configured to: converting the electroencephalogram time domain data to be detected and each electroencephalogram time domain data in each group of electroencephalogram time domain data into bitmap data in the same format, wherein one group of electroencephalogram time domain data is used for obtaining one group of bitmap data, and the other group of electroencephalogram time domain data to be detected is used for obtaining bitmap data to be detected;
the feature library construction module is configured to: for each set of bitmap data, calculating the similarity with the first bitmap data in sequence from the second bitmap data, if the similarity reaches a preset value and is not completely the same, reserving the bitmap data, otherwise discarding the bitmap data, and finally, constructing a feature library by each reserved set of bitmap data;
the feature detection module is configured to: and carrying out exclusive OR operation on the bitmap data to be detected and each piece of bitmap data in the feature library in sequence, and judging the state corresponding to the electroencephalogram time domain data if the operation result is 0.
Further, the bitmap conversion module includes a time-frequency conversion unit, a binarization unit, and a bitmap construction unit, where:
the time-frequency conversion unit converts the input electroencephalogram time domain data into electroencephalogram frequency domain data;
the binarization unit sorts and segments the electroencephalogram frequency domain data output by the time-frequency conversion unit from low frequency to high frequency, and binarizes each segment of frequency domain data by a preset power threshold value;
and the bitmap construction unit sequentially sorts each bit output by the binarization unit to construct bitmap data.
Further, the feature library construction module includes a feature comparison unit, where for each set of bitmap data, the feature comparison unit performs exclusive-or operation with the first piece of bitmap data in sequence from the second piece of bitmap data, and when the number of bits of 1 in the operation result does not exceed a predetermined number and the operation result is not 0, the piece of bitmap data is reserved, otherwise, the piece of bitmap data is discarded.
Further, the feature library construction module further includes a feature counting unit that counts the number of bitmap data reserved for each group of bitmap data, and when the count of bitmap data reserved for each group of bitmap data reaches a set maximum value, controls the feature comparing unit to discard all bitmap data after the group of bitmap data.
The invention also provides a multichannel simple mental state detection system which is characterized by comprising a computer readable storage medium and a processor, wherein the computer readable storage medium stores a computer program, and the processor runs the computer program to execute the multichannel simple mental state detection method.
The invention also provides a multichannel simple mental state detection system which is characterized by comprising an electroencephalogram time domain data acquisition device and the multichannel simple mental state detection device, wherein the electroencephalogram time domain data acquisition device is connected with the multichannel simple mental state detection device.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. the multichannel simple mental state detection scheme of the invention also obtains the electroencephalogram data of different volunteer patients under various excitation conditions, but the invention simplifies the characteristics of the electroencephalogram data, reserves the characteristics capable of reflecting the active area of the brain of the patient under the excitation conditions, simplifies the description mode (adopting bitmap description) of the characteristics in a computer, simplifies the structure of the electroencephalogram characteristics, reduces the requirement on the storage space of the system, and ensures that the characteristics have more operational capability. In addition, the calculation model is sufficiently simplified, and the feasibility of the portable detection system is improved.
2. The invention adopts the bitmap data to construct the feature library and adopts the bitmap data to perform feature comparison, thereby greatly reducing the calculation amount of the feature library construction and improving the calculation efficiency of feature detection (classification).
3. The invention can strictly control the capacity of the feature library, so that the running stability of the feature library can be maintained for more sample sizes.
Drawings
The invention will now be described by way of example and with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a multi-channel simple mental state detection method according to a preferred embodiment of the present invention.
Fig. 2 is a spatial and planar position distribution of electroencephalogram acquisition leads according to a preferred embodiment of the present invention.
Fig. 3 is a schematic diagram of frequency domain data segmentation in accordance with a preferred embodiment of the present invention.
Fig. 4 is a construction diagram of a multichannel simple mental state detection according to a preferred embodiment of the present invention.
Detailed Description
All of the features disclosed in this specification, or all of the steps in a method or process disclosed, may be combined in any combination, except for mutually exclusive features and/or steps.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.
Example 1
A multichannel simple mental state detection method, as shown in figure 1, comprises the following steps:
acquiring a multi-channel electroencephalogram time domain data set, wherein the multi-channel electroencephalogram time domain data set comprises a plurality of groups of electroencephalogram time domain data, namely, one group of electroencephalogram time domain data corresponds to one channel, and each group of electroencephalogram time domain data comprises electroencephalogram time domain data respectively obtained for a plurality of volunteer patients under the same group of excitation conditions.
Specifically, referring to fig. 2, the electroencephalogram, that is, electroencephalogram time domain data of each volunteer patient is obtained under the same group of excitation conditions (including visual and auditory stimuli) by wearing the potential cap for a plurality of volunteers or respectively, so that a group of electroencephalogram time domain data is obtained. The stimulation conditions are then exchanged and in the same way a further set of electroencephalogram time domain data can be obtained. By repeating the above steps, a plurality of sets of electroencephalogram time domain data can be obtained, namely, one set of excitation conditions corresponds to one set of electroencephalogram time domain data, and one set of excitation conditions corresponds to one mental state.
Each piece of electroencephalogram time domain data in each group of electroencephalogram time domain data is converted into bitmap data in the same format.
Each piece of bitmap data is set to the same format for convenience of storage and operation. In some embodiments, a method of converting electroencephalographic time domain data to bitmap data includes:
performing time-frequency conversion on the electroencephalogram time domain data to obtain electroencephalogram frequency domain data;
and sequencing the electroencephalogram frequency domain data from low frequency to high frequency, segmenting the sequenced frequency domain data by taking frequency as a dimension, binarizing each segment of frequency domain data by a preset power threshold value, so that each segment of frequency domain data has one-bit binarization confusion, and sequencing each bit after binarization in the original frequency sequence to obtain bitmap data.
In general, important information of frequency domain data corresponding to an electroencephalogram is concentrated in 0.5 to 50Hz, and for this frequency band, it is medically expressed as delta wave (0.5 to 4 Hz), theta wave (4 to 7 Hz), alpha wave (7 to 13 Hz), beta wave (13 to 25 Hz), and gamma wave (25 to 50 Hz). Each band is active in different areas of the brain and represents different brain physiological activities and functions. When the electroencephalogram time domain data is subjected to time-frequency conversion to obtain electroencephalogram frequency domain data, the electroencephalogram frequency domain data can be filtered to filter signals lower than 0.5Hz and higher than 50 Hz. Furthermore, in the segmentation of the electroencephalogram frequency, the frequency bands can be divided evenly according to reserved frequency bands, and the frequency bands can be divided according to the medical expression. For example, the frequency domain data is divided into 10 frequency bands, 0.5-4Hz, 4-7Hz, 7-13Hz, 13-19Hz, 19-25Hz, 25-30Hz, 30-35Hz, 35-40Hz, 40-45Hz, and 45-50Hz, as shown in FIG. 3. The segmentation method can also adopt other non-average methods, such as non-average division of gamma wave bands or average division of continuous wave bands of beta waves and gamma waves. If the high-precision characteristic is required to be obtained, the number of the divided wave bands is correspondingly increased. The manner in which the pair of frequency data is segmented may be applied to subsequent apparatus embodiments.
One electroencephalogram time domain data corresponds to one electroencephalogram frequency domain data, one bitmap data is obtained through processing, and one group of electroencephalogram time domain data corresponds to one group of bitmap data. Taking the above example of dividing the frequency domain data into 10 segments, a set of 10 pieces of bitmap data includes: 0001011101, 0011011101, 0001011101, 0001011100, 0011011101, 0001011101, 0001010101, 0001011101, 0101011101, 0011011101. The same method is used for obtaining corresponding bitmap data to be detected from electroencephalogram time domain data to be detected. The electroencephalogram time domain data to be detected can be obtained during subsequent detection, and can also be obtained together during the first step of obtaining the multichannel electroencephalogram time domain data set, and is usually obtained after the feature library is built.
For each set of bitmap data, calculating the similarity with the first piece of bitmap data from the second piece of bitmap data in sequence, and when the similarity reaches a preset value and is not completely the same, retaining the piece of bitmap data, otherwise discarding the piece of bitmap data. Thus, a plurality of reserved bitmap data are obtained for each group of bitmap data, each reserved bitmap data corresponds to a mental state, and finally each reserved bitmap data constitutes a feature library.
Because the same symptoms and the same excitation conditions exist, bitmap data corresponding to electroencephalogram time domain data of a plurality of volunteer patients are allowed to have certain personality differences, but are highly similar, so that the characteristics corresponding to the same mental state are required to be concentrated, and data with large differences (qualitative noise data) are excluded to have specificity, so that bitmap data with high similarity with the first piece of bitmap data but not identical are reserved, and bitmap data with large differences are discarded, and if the bitmap data with identical differences are reserved, the data are repeated. The method for calculating the similarity may be in various ways, which will be described in detail later.
Further, the capacity of each set of bitmap data to be reserved needs to be limited to a certain extent, so that the specificity of each mental state is improved, and the running stability of the feature library is ensured. In some embodiments, the number of bitmap data corresponding to each group of electroencephalogram time domain data is set to a maximum value; when the number of bitmap data obtained reaches the maximum value, all bitmap data after the bitmap data is discarded. The maximum value belongs to an empirical value, and is determined according to the required detection precision, so that the maximum value is smaller for high-precision requirements, and can be increased in a proper amount for coarse-precision requirements (such as full-looking-up required scenes).
Further, to further improve the specificity of the reserved features, when the number of reserved bitmap data reaches the maximum value, the similarity with the first piece of bitmap data can still be calculated for each piece of bitmap data, the similarity with each piece of reserved bitmap data and the first piece of bitmap data is compared, when the newly calculated similarity is not the minimum, the bitmap data with the lowest similarity in the original reserved bitmap data is replaced by the new bitmap data, namely, when the newly calculated bitmap data is more similar to the first piece of bitmap data than each piece of reserved bitmap data, the bitmap data with the least similarity in the original reserved bitmap data is replaced by the new bitmap data. Of course, the bitmap data for replacement cannot be identical to the first piece of bitmap data.
Finally, carrying out exclusive OR operation on the bitmap data to be tested and each piece of bitmap data in the feature library in sequence, and judging that the mental state corresponding to the bitmap data subjected to exclusive OR budget is the mental state of the person to be tested if the result of the operation is 0.
Example two
The present embodiment discloses a method of reserving or discarding each piece of bitmap data in each set of bitmap data.
In one embodiment, the calculation of the similarity between bitmap data may be determined by extracting features of the bitmap data and calculating a similarity distance (such as a common euclidean distance) between the features, where the similarity is low if the similarity distance exceeds a predetermined threshold, and otherwise, the similarity is high if the similarity distance is within the predetermined threshold. And for each group of bitmap data, respectively extracting the characteristics of each piece of bitmap data, respectively calculating the similar distance between the characteristics of the bitmap data and the first piece of bitmap data from the second piece of bitmap data, and when the similar distance is within a preset threshold value and the similar distance is not 0, reserving the bitmap data corresponding to the characteristics, otherwise, losing the bitmap data corresponding to the characteristics.
In another embodiment, the similarity determination is performed by a logical operation of the bitmap data: and carrying out exclusive or operation on the two groups of bitmap data, wherein in an operation result, if the number of bits of 1 does not exceed the preset number, the two groups of bitmap data are regarded as being highly similar, otherwise, the number of bits of 1 exceeds the preset number, and the similarity is regarded as being low. Then for each set of bitmap data, starting from the second bitmap data, performing exclusive-or operation with the first bitmap data in turn, when the number of bits of 1 in the operation result does not exceed the predetermined number, and the operation result is not 0, retaining the bitmap data, otherwise discarding the bitmap data.
Example III
The embodiment discloses a simple multichannel mental state detection device, as shown in fig. 4, comprising a data acquisition module, a bitmap conversion module, a feature library construction module and a feature detection module, wherein:
the data acquisition module is configured to: acquiring a multi-channel electroencephalogram time domain data set, wherein the multi-channel electroencephalogram time domain data set comprises a plurality of groups of electroencephalogram time domain data, and each group of electroencephalogram time domain data comprises electroencephalogram time domain data respectively obtained for a plurality of individuals under the same group of excitation conditions. The electroencephalogram time domain data to be detected can also be acquired by the data acquisition module.
The bitmap conversion module is configured to: and converting each piece of electroencephalogram time domain data in the electroencephalogram time domain data to be detected (namely electroencephalogram time domain data of a patient to be detected) and each piece of electroencephalogram time domain data in each group of electroencephalogram time domain data (of a volunteer patient) into bitmap data in the same format, wherein one group of electroencephalogram time domain data is used for obtaining one group of bitmap data, and the other group of electroencephalogram time domain data to be detected is used for obtaining bitmap data to be detected.
The bitmap conversion module comprises a time-frequency conversion unit, a binarization unit and a bitmap construction unit, wherein:
the time-frequency conversion unit converts the input electroencephalogram time domain data into electroencephalogram frequency domain data;
the binarization unit sorts and segments the electroencephalogram frequency domain data output by the time-frequency conversion unit from low frequency to high frequency, and binarizes each segment of frequency domain data with a preset power threshold value;
and the bitmap construction unit sequentially sorts each bit output by the binarization unit according to the original frequency sequence to construct bitmap data.
The feature library construction module is configured to: and for each set of bitmap data, calculating the similarity with the first bitmap data in sequence from the second bitmap data, and when the similarity reaches a preset value and is not completely the same, reserving the bitmap data, otherwise discarding the bitmap data, and finally, constructing a feature library by each reserved set of bitmap data.
Referring to the second embodiment, the feature library construction module may also perform similarity comparison between bitmap data in a plurality of ways.
In one embodiment, the feature library construction module includes a feature extraction unit, a similarity comparison unit, and a feature construction unit. The feature extraction unit extracts features of the bitmap data, and the similarity comparison unit calculates a similarity distance between the features of the bitmap data. According to this embodiment, for the construction of the feature library, for each set of bitmap data, the feature extraction unit extracts the features of each piece of bitmap data, the similarity comparison unit sequentially calculates, from the second piece of bitmap data, the similarity distances to the features of the first piece of bitmap data, and when the similarity distances are within a predetermined threshold value, and when the similarity distances are not 0, the bitmap data corresponding to the features is retained, otherwise the corresponding bitmap data is discarded. The feature construction unit constructs a feature library using each set of bitmap data that is reserved.
In another embodiment, the feature library construction module includes a feature comparing unit and a feature construction unit, where the feature comparing unit performs exclusive-or operation with the first piece of bitmap data in sequence from the second piece of bitmap data for each group of bitmap data, and when the number of bits of 1 in the operation result does not exceed the predetermined number and the operation result is not 0, the piece of bitmap data is reserved, otherwise, the piece of bitmap data is discarded.
Further, the feature library construction unit further includes a feature counting unit that counts the number of bitmap data held by each set of bitmap data, and when the count of bitmap data held by each set of bitmap data reaches a set maximum value, controls the feature comparing unit to discard all bitmap data after the set of bitmap data.
Alternatively, in the case of the above-described first embodiment, when the count of the feature count unit reaches the maximum value, the similarity comparing unit continues to calculate the similarity distance between the feature of each piece of the subsequent bitmap data and the feature of the first piece of bitmap data, compares the similarity distance with the similarity distance between the feature of each piece of the reserved bitmap data and the feature of the first piece of bitmap data, and replaces the bitmap data having the largest similarity distance with the feature of the first piece of bitmap data, among the reserved bitmap data, when the similarity distance is smaller than the similarity distance between the feature of a certain piece of the reserved bitmap data and the feature of the first piece of bitmap data.
With the second embodiment, when the count of the feature counting unit reaches the maximum value, the feature comparing unit continues to perform the exclusive-or operation on each subsequent piece of bitmap data and the first piece of bitmap data, and when the number of bits of the calculated result 1 is less than the number of bits of the reserved bitmap data and the number of bits of 1 in the exclusive-or result of the first piece of bitmap data, replaces the piece of bitmap data with the largest number of bits of 1 in the exclusive-or result of the reserved bitmap data and the first piece of bitmap data.
The feature detection module is configured to: and carrying out exclusive OR operation on the bitmap data to be detected and each piece of bitmap data in the feature library in sequence, and judging the mental state corresponding to the electroencephalogram time domain data corresponding to a certain piece of bitmap data if the operation result of the bitmap data and the bitmap data is 0.
Example IV
The embodiment discloses a multichannel simple mental state detection system, which comprises a computer readable storage medium and a processor, wherein the computer readable storage medium stores a computer program, the processor runs the computer program to execute the multichannel simple mental state detection method of the first embodiment, and the method can be applied to the method for reserving or discarding bitmap data in the second embodiment.
Or in another embodiment, the multichannel simple mental state detection system comprises an electroencephalogram time domain data acquisition device and the multichannel simple mental state detection device in the third embodiment, wherein the electroencephalogram time domain data acquisition device is connected with the multichannel simple mental state detection device so as to transmit the acquired electroencephalogram time domain data to the multichannel simple mental state detection device for detection.
The invention is not limited to the specific embodiments described above. The invention extends to any novel one, or any novel combination, of the features disclosed in this specification, as well as to any novel one, or any novel combination, of the steps of the method or process disclosed.
Claims (10)
1. A multi-channel simple mental state detection method, comprising:
acquiring a multi-channel electroencephalogram time domain data set, wherein the multi-channel electroencephalogram time domain data set comprises a plurality of groups of electroencephalogram time domain data, and each group of electroencephalogram time domain data comprises electroencephalogram time domain data respectively obtained for a plurality of individuals under the same group of excitation conditions;
converting each electroencephalogram time domain data in each group of electroencephalogram time domain data into bitmap data in the same format, and obtaining a group of bitmap data by one group of electroencephalogram time domain data;
for each set of bitmap data, calculating the similarity with the first bitmap data in sequence from the second bitmap data, if the similarity reaches a preset value and is not completely the same, reserving the bitmap data, otherwise discarding the bitmap data, and finally, constructing a feature library by each reserved set of bitmap data;
converting the electroencephalogram time domain data to be detected into bitmap data with the same format as bitmap data in a feature library to obtain bitmap data to be detected; and carrying out exclusive OR operation on the bitmap data to be detected and each piece of bitmap data in the feature library in sequence, and judging the state corresponding to the electroencephalogram time domain data if the operation result is 0.
2. The multi-channel simple mental state detection method according to claim 1, wherein the converting each piece of electroencephalogram time domain data in each set of electroencephalogram time domain data into bitmap data of the same format, comprises:
the following processing is performed on each piece of electroencephalogram time domain data in each group of electroencephalogram time domain data:
performing time-frequency conversion on the electroencephalogram time domain data to obtain electroencephalogram frequency domain data;
and sequencing and segmenting the electroencephalogram frequency domain data from low frequency to high frequency, binarizing each segment of frequency domain data with a preset power threshold value, and sequencing each bit after binarization in sequence to obtain bitmap data.
3. The multi-channel easy mental state detection method according to claim 1, wherein the sequentially calculating the similarity with the first piece of bitmap data from the second piece of bitmap data, and retaining the piece of bitmap data when the similarity reaches a predetermined value, otherwise discarding the piece of bitmap data, comprises:
and (3) starting from the second bitmap data, sequentially carrying out exclusive OR operation with the first bitmap data, and when the number of bits of 1 in the operation result does not exceed the preset number and the operation result is not 0, reserving the bitmap data, otherwise discarding the bitmap data.
4. The multi-channel simple mental state detection method according to claim 1 or 3, wherein the number of bitmap data corresponding to each group of electroencephalogram time domain data is set to a maximum value; when the number of bitmap data obtained reaches the maximum value, all bitmap data after the bitmap data is discarded.
5. The multichannel simple mental state detection device is characterized by comprising a data acquisition module, a bitmap conversion module, a feature library construction module and a feature detection module, wherein:
the data acquisition module is configured to: acquiring a multi-channel electroencephalogram time domain data set, wherein the multi-channel electroencephalogram time domain data set comprises a plurality of groups of electroencephalogram time domain data, and each group of electroencephalogram time domain data comprises electroencephalogram time domain data respectively obtained for a plurality of individuals under the same group of excitation conditions;
the bitmap conversion module is configured to: converting the electroencephalogram time domain data to be detected and each electroencephalogram time domain data in each group of electroencephalogram time domain data into bitmap data in the same format, wherein one group of electroencephalogram time domain data is used for obtaining one group of bitmap data, and the other group of electroencephalogram time domain data to be detected is used for obtaining bitmap data to be detected;
the feature library construction module is configured to: for each set of bitmap data, calculating the similarity with the first bitmap data in sequence from the second bitmap data, if the similarity reaches a preset value and is not completely the same, reserving the bitmap data, otherwise discarding the bitmap data, and finally, constructing a feature library by each reserved set of bitmap data;
the feature detection module is configured to: and carrying out exclusive OR operation on the bitmap data to be detected and each piece of bitmap data in the feature library in sequence, and judging the state corresponding to the electroencephalogram time domain data if the operation result is 0.
6. The multi-channel simple mental state detection apparatus according to claim 5, wherein the bitmap conversion module comprises a time-frequency conversion unit, a binarization unit, and a bitmap construction unit, wherein:
the time-frequency conversion unit converts the input electroencephalogram time domain data into electroencephalogram frequency domain data;
the binarization unit sorts and segments the electroencephalogram frequency domain data output by the time-frequency conversion unit from low frequency to high frequency, and binarizes each segment of frequency domain data by a preset power threshold value;
and the bitmap construction unit sequentially sorts each bit output by the binarization unit to construct bitmap data.
7. The multi-channel simple mental state detection apparatus according to claim 5, wherein the feature library construction module comprises a feature comparison unit that sequentially exclusive-ors the first piece of bitmap data from the second piece of bitmap data for each set of bitmap data, and retains the piece of bitmap data when the number of bits of 1 in the operation result does not exceed a predetermined number and the operation result is not 0, otherwise discards the piece of bitmap data.
8. The multi-channel simple mental state detection apparatus according to claim 7, wherein the feature library construction module further comprises a feature counting unit that counts the number of bitmap data held by each set of bitmap data, and when the count of bitmap data held by each set of bitmap data reaches a set maximum value, controls the feature comparing unit to discard all bitmap data after the set of bitmap data.
9. A multichannel easy mental state detection system, characterized by comprising a computer readable storage medium storing a computer program and a processor running the computer program to perform the multichannel easy mental state detection method according to any of claims 1 to 4.
10. A multichannel simple mental state detection system, characterized by comprising an electroencephalogram time domain data acquisition device and a multichannel simple mental state detection device according to any one of claims 5 to 8, wherein the electroencephalogram time domain data acquisition device is connected with the multichannel simple mental state detection device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310587769.7A CN116616771B (en) | 2023-05-23 | 2023-05-23 | Multichannel simple mental state detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310587769.7A CN116616771B (en) | 2023-05-23 | 2023-05-23 | Multichannel simple mental state detection method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116616771A true CN116616771A (en) | 2023-08-22 |
| CN116616771B CN116616771B (en) | 2024-01-26 |
Family
ID=87601990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310587769.7A Active CN116616771B (en) | 2023-05-23 | 2023-05-23 | Multichannel simple mental state detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116616771B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502047A (en) * | 2023-05-23 | 2023-07-28 | 成都市第四人民医院 | Method and system for processing biomedical data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10262943A (en) * | 1997-01-24 | 1998-10-06 | Yamaha Corp | Method, instrument for measuring electroencephalogram, method and device for transmitting will using the measuring method |
| CN1333003A (en) * | 2001-07-13 | 2002-01-30 | 天津大学 | Method for forming brain scalp electric potential information chart |
| CN102170315A (en) * | 2009-09-28 | 2011-08-31 | 特克特朗尼克公司 | Frequency domain bitmap trigger |
| US20190059762A1 (en) * | 2017-08-24 | 2019-02-28 | Myneurva Holdings, Inc. | System and method for analyzing electroencephalogram signals |
| CN110338760A (en) * | 2019-07-01 | 2019-10-18 | 上海交通大学 | A kind of three classification method of schizophrenia based on electroencephalogram frequency domain data |
| CN111626153A (en) * | 2020-05-13 | 2020-09-04 | 电子科技大学 | Integrated learning-based partial discharge fault state identification method |
| CN111671421A (en) * | 2020-06-24 | 2020-09-18 | 安徽智趣小天使信息科技有限公司 | Electroencephalogram-based children demand sensing method |
| CN115500841A (en) * | 2022-09-26 | 2022-12-23 | 浙江大学 | Ventricular premature beat positioning method for fusion of time domain and frequency domain feature deep learning |
-
2023
- 2023-05-23 CN CN202310587769.7A patent/CN116616771B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10262943A (en) * | 1997-01-24 | 1998-10-06 | Yamaha Corp | Method, instrument for measuring electroencephalogram, method and device for transmitting will using the measuring method |
| CN1333003A (en) * | 2001-07-13 | 2002-01-30 | 天津大学 | Method for forming brain scalp electric potential information chart |
| CN102170315A (en) * | 2009-09-28 | 2011-08-31 | 特克特朗尼克公司 | Frequency domain bitmap trigger |
| US20190059762A1 (en) * | 2017-08-24 | 2019-02-28 | Myneurva Holdings, Inc. | System and method for analyzing electroencephalogram signals |
| CN110338760A (en) * | 2019-07-01 | 2019-10-18 | 上海交通大学 | A kind of three classification method of schizophrenia based on electroencephalogram frequency domain data |
| CN111626153A (en) * | 2020-05-13 | 2020-09-04 | 电子科技大学 | Integrated learning-based partial discharge fault state identification method |
| CN111671421A (en) * | 2020-06-24 | 2020-09-18 | 安徽智趣小天使信息科技有限公司 | Electroencephalogram-based children demand sensing method |
| CN115500841A (en) * | 2022-09-26 | 2022-12-23 | 浙江大学 | Ventricular premature beat positioning method for fusion of time domain and frequency domain feature deep learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502047A (en) * | 2023-05-23 | 2023-07-28 | 成都市第四人民医院 | Method and system for processing biomedical data |
| CN116502047B (en) * | 2023-05-23 | 2024-05-07 | 成都市第四人民医院 | Method and system for processing biomedical data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116616771B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107495962B (en) | Sleep automatic staging method for single-lead electroencephalogram | |
| Sulaiman et al. | Novel methods for stress features identification using EEG signals | |
| CN111466876B (en) | Alzheimer's disease auxiliary diagnosis system based on fNIRS and graph neural network | |
| CN104173046B (en) | A kind of extracting method of color indicia Amplitude integrated electroencephalogram | |
| CN106413541B (en) | System and method for diagnosing sleep | |
| CN105559779A (en) | Method for carrying out cognitive evaluation through electroencephalo-graph frequency spectrum | |
| CN116616771B (en) | Multichannel simple mental state detection method, device and system | |
| Roy et al. | Photoplethysmogram signal quality evaluation by unsupervised learning approach | |
| CN113768519A (en) | Method for analyzing consciousness level of patient based on deep learning and resting state electroencephalogram data | |
| CN114081439A (en) | Brain-like algorithm for sleep staging by applying prefrontal single-channel electroencephalogram signals | |
| Zhou et al. | Both cross-patient and patient-specific seizure detection based on self-organizing fuzzy logic | |
| Hussain et al. | A healthcare digital twin for diagnosis of stroke | |
| Yang et al. | Cross-subject classification of depression by using multiparadigm EEG feature fusion | |
| Al-Qazzaz et al. | Complexity and Entropy Analysis to Improve Gender Identification from Emotional‐Based EEGs | |
| Jiang et al. | Early seizure detection in childhood focal epilepsy with electroencephalogram feature fusion on deep autoencoder learning and channel correlations | |
| Siuly et al. | Exploring Rhythms and Channels-Based EEG Biomarkers for Early Detection of Alzheimer's Disease | |
| Song et al. | Optimization of epilepsy detection method based on dynamic EEG channel screening | |
| da Silva Lourenço et al. | Ultrafast review of ambulatory EEGs with deep learning | |
| Rajendran et al. | An overview of EEG seizure detection units and identifying their complexity-A review | |
| Nirabi et al. | Machine Learning-Based Stress Level Detection from EEG Signals | |
| Tiwary et al. | Deep learning with spatial and channel attention for epileptic seizure type classification using frequency characterization | |
| Lobacheva et al. | Automated real-time classification of functional states based on physiological parameters | |
| Cruz et al. | EEG-based characterization and classification of severity for the diagnosis of post-traumatic stress disorder (PTSD) | |
| Al-Qazzaz et al. | Recognition enhancement of dementia patients’ working memory using entropy-based features and local tangent space alignment algorithm | |
| CN116502047B (en) | Method and system for processing biomedical data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |